draft
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill passes user-provided input ($ARGUMENTS) directly to the /workflows:plan command without sanitization or boundary markers.\n
- Ingestion points: User input via $ARGUMENTS in SKILL.md.\n
- Boundary markers: None present to distinguish user input from command instructions.\n
- Capability inventory: Invokes the /workflows:plan workflow tool.\n
- Sanitization: No input validation or escaping is performed on the arguments.
Audit Metadata